Heap-based Buffer OverflowWeakness · CWE-122

CVE-2026-47471

HIGH · 7.5 CVSS v3.1 Published 2026-07-14
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
80/100
Remediation priority · High
No privileges Zero-click 5 weeks old

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
NVIDIA TensorRT-LLM for any platform contains a vulnerability in tensor deserialization, where an attacker could cause a heap based buffer overflow. A successful exploit of this vulnerability might lead to information disclosure, data tampering, or denial of service.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · moderate confidence

NVIDIA TensorRT-LLM contains a heap-based buffer overflow vulnerability in its tensor deserialization functionality. During the loading or deserialization of tensor data, the application fails to properly validate buffer sizes before writing data, allowing an attacker to overflow heap memory boundaries. This could enable information disclosure through memory leakage, data tampering by corrupting adjacent heap structures, or denial of service via application crash.

MitigationApply any vendor-supplied patches or updates to TensorRT-LLM when released by NVIDIA. In the interim, implement strict input validation on any model or tensor data before deserialization, restrict model loading to trusted sources only, and consider deploying memory protection mechanisms such as sandboxing or runtime application self-protection (RASP) to detect heap corruption patterns.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Adjacent
Complexity
High
Privileges
None
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:A/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Confirm TensorRT-LLM installation
    Run 'pip show tensorrt-llm' or check for the tensorrt_llm Python package in your environment
    Affected if The package is not installed or the command fails, indicating TensorRT-LLM is not present
  2. Identify installed TensorRT-LLM version
    Execute 'pip show tensorrt-llm' and note the Version field, or import tensorrt_llm and print(tensorrt_llm.__version__)
    Affected if A version is returned that falls within any affected version range (compare your version to vendor advisories)
  3. Verify tensor loading from external sources
    Review application logs, code, or configuration for calls to tensor loading functions such as 'fromfile', 'load', 'deserialize', or TensorRT tensor deserialization APIs when loading models from untrusted paths
    Affected if The application loads tensors or model files from untrusted or user-controlled sources without validation
  4. Check for deserialization of untrusted tensor data
    Inspect any model loading pipelines, inference scripts, or custom operators that deserialize tensors, and verify if the data source is from trusted locations only
    Affected if Tensor deserialization is performed on data from untrusted or network-accessible sources
  5. Audit memory allocation for tensor operations
    Enable memory debugging tools such as Valgrind or address sanitizer (ASAN) during tensor loading operations to detect heap buffer overflows
    Affected if Heap buffer overflows are detected during tensor deserialization or model loading

Your environment is affected if TensorRT-LLM is installed and you load or deserialize tensors from untrusted sources without validating buffer sizes first.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

From vendor data
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Apply any vendor-supplied patches or updates to TensorRT-LLM when released by NVIDIA. In the interim, implement strict input validation on any model or tensor data before deserialization, restrict model loading to trusted sources only, and consider deploying memory protection mechanisms such as sandboxing or runtime application self-protection (RASP) to detect heap corruption patterns.

Have this fixed Scoped from the published advisory
  • Consultation4.0 h
  • Implementation8.0 h
  • Testing6.0 h
  • Review / QA3.0 h
21.0 hours of engineering $3,680
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $5,888.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-47471 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-47471 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data